{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:16:16Z","timestamp":1785428176028,"version":"3.56.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T00:00:00Z","timestamp":1641340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Program of Scientific and Technological Research of Henan Province","award":["192102310215"],"award-info":[{"award-number":["192102310215"]}]},{"name":"the Key Science & Research Program of Henan Province","award":["21A520044"],"award-info":[{"award-number":["21A520044"]}]},{"name":"the China Education and Research Network (CERNET) Innovation Project","award":["NGII20180708"],"award-info":[{"award-number":["NGII20180708"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>TOAST subtype classification is important for diagnosis and research of ischemic stroke. Limited by experience of neurologist and time-consuming manual adjudication, it is a big challenge to finish TOAST classification effectively. We propose a novel active deep learning architecture to classify TOAST.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>To simulate the diagnosis process of neurologists, we drop the valueless features by XGB algorithm and rank the remaining ones. Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively. Meanwhile, KL-focal loss derived from the enhancement of Focal loss by KL regularization is introduced to accelerate the iterative fine-tuning of the model.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>To evaluate the proposed method, we construct a dataset which consists of totally 2310 patients. In a series of sequential experiments, we verify the effectiveness of each contribution by different evaluation metrics. Experimental results show that the proposed method achieves competitive results on each evaluation metric. In this task, the improvement of AUC is the most obvious, reaching 77.4.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>We construct a backbone causal CNN to simulate the neurologist process of that could enhance the internal interpretability. The research on clinical data also indicates the potential application value of this model in stroke medicine. Future work we would consider various data types and more comprehensive patient types to achieve fully automated subtype classification.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-021-01721-5","type":"journal-article","created":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T12:05:59Z","timestamp":1641384359000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Interpretable CNN for ischemic stroke subtype classification with active model adaptation"],"prefix":"10.1186","volume":"22","author":[{"given":"Shuo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Honghua","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runzhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuming","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,5]]},"reference":[{"key":"1721_CR1","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/S1474-4422(21)00252-0","volume":"20","author":"V Feigin","year":"2021","unstructured":"Feigin V, Stark B, Johnson C, Roth G, Bisignano C, Abady G, Abbasifard M, Abbasi-Kangevari M, Abd-Allah F, Abedi V, Abualhasan A, Abu-Rmeileh N, I.\u00a0Abushouk A, Oyabeda I, Agarwal G, Agasthi P, Ahinkorah B, Ahmad S, Ahmadi S, Murray C. Global, regional, and national burden of stroke and its risk factors, 1990\u20132019: a systematic analysis for the global burden of disease study 2019. Lancet Neurol. 2021;20:795\u2013820.","journal-title":"Lancet Neurol"},{"key":"1721_CR2","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1055\/s-0038-1649503","volume":"38","author":"M Katan","year":"2018","unstructured":"Katan M, Luft A. Global burden of stroke. Semin Neurol. 2018;38:208\u201311.","journal-title":"Semin Neurol"},{"issue":"6","key":"1721_CR3","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1016\/j.jfma.2020.11.014","volume":"120","author":"YC Wu","year":"2021","unstructured":"Wu YC, Lo WC, Lu TH, Chang SS, Lin HH, Chan CC. Mortality, morbidity, and risk factors in Taiwan, 1990\u20132017: findings from the global burden of disease study 2017. J Formos Med Assoc. 2021;120(6):1340\u20139.","journal-title":"J Formos Med Assoc"},{"key":"1721_CR4","first-page":"139","volume":"54","author":"Y Wang","year":"2021","unstructured":"Wang Y. Secondary prevention for ischemic stroke. Chin J Neurol. 2021;54:139\u201348.","journal-title":"Chin J Neurol"},{"key":"1721_CR5","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1111\/ane.12589","volume":"135","author":"ML Schmitz","year":"2016","unstructured":"Schmitz ML, Simonsen CZ, Svendsen ML, Larsson H, Madsen MH, Mikkelsen IK, Fisher M, Johnsen SP, Andersen G. Ischemic stroke subtype is associated with outcome in thrombolyzed patients. Acta Neurol Scand. 2016;135:176\u201382.","journal-title":"Acta Neurol Scand"},{"key":"1721_CR6","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1212\/WNL.28.8.754","volume":"28","author":"JP Mohr","year":"1978","unstructured":"Mohr JP, Caplan LR, Melski JW, Goldstein RJ, Duncan GW, Kistler JP, Pessin MS, Bleich HL. The Harvard cooperative stroke registry: a prospective registry. Neurology. 1978;28:754\u201362.","journal-title":"Neurology"},{"key":"1721_CR7","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1161\/01.STR.19.5.547","volume":"19","author":"MA Foulkes","year":"1988","unstructured":"Foulkes MA, Wolf PA, Price TR, Mohr JP, Hier DB. The stroke data bank: design, methods, and baseline characteristics. Stroke. 1988;19:547.","journal-title":"Stroke"},{"key":"1721_CR8","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1136\/jnnp.53.10.824","volume":"53","author":"J Bamford","year":"1990","unstructured":"Bamford J, Dennis M, Sandercock P, Burn J, Warlow C. The frequency, causes and timing of death within 30 days of a first stroke: the Oxfordshire community stroke project. J Neurol Neurosurg Psychiatry. 1990;53:824\u20139.","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"1721_CR9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1161\/01.STR.24.1.35","volume":"24","author":"HP Adams","year":"1993","unstructured":"Adams HP, Bendixen BH, Kappelle LJ. Biller: classification of subtype of acute ischemic stroke. Definitions for use in a multicenter clinical trial. toast. trial of org 10172 in acute stroke treatment. Stroke. 1993;24:35\u201341.","journal-title":"Stroke"},{"key":"1721_CR10","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1111\/ane.13201","volume":"141","author":"EG Malek","year":"2019","unstructured":"Malek EG, Elbejjani M, Abbas R, Ahad MAA, Makki A. Toast classification and risk factors of ischemic stroke in Lebanon. Acta Neurol Scand. 2019;141:294\u2013300.","journal-title":"Acta Neurol Scand"},{"key":"1721_CR11","first-page":"e11388","volume":"12","author":"V Moond","year":"2020","unstructured":"Moond V, Bansal K, Jain R. Risk factors and subtyping of ischemic stroke in young adults in the Indian population. Cureus. 2020;12:e11388.","journal-title":"Cureus"},{"key":"1721_CR12","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1161\/STROKEAHA.117.020031","volume":"49","author":"R Ornello","year":"2018","unstructured":"Ornello R, Degan D, Tiseo C, Carmine CD, Perciballi L, Pistoia F, Carolei A, Sacco S. Distribution and temporal trends from 1993 to 2015 of ischemic stroke subtypes: a systematic review and meta-analysis. Stroke. 2018;49:814\u20139.","journal-title":"Stroke"},{"key":"1721_CR13","unstructured":"Hosseini MP, Hemingway C, Madamba J, Mckee A, Voss E. Review of machine learning algorithms for brain stroke diagnosis and prognosis by EEG analysis. 2020."},{"key":"1721_CR14","doi-asserted-by":"crossref","unstructured":"Emon MU, Keya MS, Meghla TI, Rahman MM, Kaiser MS. Performance analysis of machine learning approaches in stroke prediction. In: Proceedings of performance analysis of machine learning approaches in stroke prediction. 2021.","DOI":"10.1109\/ICECA49313.2020.9297525"},{"key":"1721_CR15","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1111\/ene.14295","volume":"27","author":"X Li","year":"2020","unstructured":"Li X, Wu M, Sun C, Zhao Z, Zou J. Using machine learning to predict stroke-associated pneumonia in Chinese acute ischaemic stroke patients. Eur J Neurol. 2020;27:1656\u201363.","journal-title":"Eur J Neurol"},{"key":"1721_CR16","doi-asserted-by":"publisher","first-page":"107316","DOI":"10.1016\/j.compbiolchem.2020.107316","volume":"88","author":"G Fang","year":"2020","unstructured":"Fang G, Liu W, Wang L. A machine learning approach to select features important to stroke prognosis. Comput Biol Chem. 2020;88:107316.","journal-title":"Comput Biol Chem"},{"key":"1721_CR17","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/s00521-019-04041-y","volume":"32","author":"P Govindarajan","year":"2020","unstructured":"Govindarajan P, Soundarapandian RK, Gandomi AH, Patan R, Jayaraman P, Manikandan R. Classification of stroke disease using machine learning algorithms. Neural Comput Appl. 2020;32:817\u201328.","journal-title":"Neural Comput Appl"},{"key":"1721_CR18","unstructured":"Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K. Wavenet: a generative model for raw audio. 2016."},{"key":"1721_CR19","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin TY, Goyal P, Girshick R, He K, Dollar P. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell. 2020;42:318\u201327.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1721_CR20","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"1721_CR21","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1016\/j.jstrokecerebrovasdis.2019.02.004","volume":"28","author":"R Garg","year":"2019","unstructured":"Garg R, Oh E, Naidech A, Kording K, Prabhakaran S. Automating ischemic stroke subtype classification using machine learning and natural language processing. J Stroke Cerebrovasc Dis. 2019;28:2045\u201351.","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"1721_CR22","unstructured":"Terriza LJ, Martin JL, Ayala JL. Comparison of different machine learning approaches to model stroke subtype classification and risk prediction. In: Proceedings of 2019 spring simulation conference (SpringSim). 2019."},{"key":"1721_CR23","doi-asserted-by":"publisher","first-page":"118426","DOI":"10.1109\/ACCESS.2020.3004977","volume":"8","author":"G Fang","year":"2020","unstructured":"Fang G, Xu P, Liu W. Automated ischemic stroke subtyping based on machine learning approach. IEEE Access. 2020;8:118426\u201332.","journal-title":"IEEE Access"},{"key":"1721_CR24","doi-asserted-by":"publisher","first-page":"2922","DOI":"10.1109\/JBHI.2020.2976931","volume":"24","author":"SF Sung","year":"2020","unstructured":"Sung SF, Lin CY, Hu YH. EMR-based phenotyping of ischemic stroke using supervised machine learning and text mining techniques. IEEE J Biomed Health Inform. 2020;24:2922\u201331.","journal-title":"IEEE J Biomed Health Inform"},{"key":"1721_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-020-1106-3","volume":"20","author":"L Qin","year":"2020","unstructured":"Qin L, Xu X, Ding L, et al. Identifying diagnosis evidence of cardiogenic stroke from Chinese echocardiograph reports. BMC Med Inform Decis Mak. 2020;20:1\u201311.","journal-title":"BMC Med Inform Decis Mak"},{"key":"1721_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-018-0723-6","volume":"19","author":"X Li","year":"2019","unstructured":"Li X, Bian D, Yu J, et al. Using machine learning models to improve stroke risk level classification methods of China national stroke screening. BMC Med Inform Decis Mak. 2019;19:1\u201317.","journal-title":"BMC Med Inform Decis Mak"},{"key":"1721_CR27","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1161\/01.STR.32.5.1091","volume":"32","author":"LB Goldstein","year":"2001","unstructured":"Goldstein LB, Jones MR, Matchar DB, Edwards LJ, Hoff J, Chilukuri V, Armstrong SB, Horner RD. Improving the reliability of stroke subgroup classification using the trial of org 10172 in acute stroke treatment (toast) criteria. Stroke. 2001;32:1091\u20138.","journal-title":"Stroke"},{"key":"1721_CR28","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1002\/ana.20617","volume":"58","author":"H Ay","year":"2010","unstructured":"Ay H, Furie KL, Singhal A, Smith WS, Koroshetz WJ. An evidence-based causative classification system for acute ischemic stroke. Ann Neurol. 2010;58:688\u201397.","journal-title":"Ann Neurol"},{"key":"1721_CR29","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.1161\/STROKEAHA.107.490896","volume":"38","author":"H Ay","year":"2007","unstructured":"Ay H, Benner T, Arsava EM, Furie KL, Sorensen AG. A computerized algorithm for etiologic classification of ischemic stroke the causative classification of stroke system. Stroke. 2007;38:2979\u201384.","journal-title":"Stroke"},{"key":"1721_CR30","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1159\/000098059","volume":"57","author":"SW Han","year":"2007","unstructured":"Han SW, Kim SH, Lee JY, Chu CK, Yang JH, Shin HY, Nam HS, Lee BI, Heo JH. A new subtype classification of ischemic stroke based on treatment and etiologic mechanism. Eur Neurol. 2007;57:96\u2013102.","journal-title":"Eur Neurol"},{"key":"1721_CR31","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3389\/fneur.2011.00006","volume":"2","author":"S Gao","year":"2011","unstructured":"Gao S, Wang YJ, Xu AD, Li YS, Wang DZ. Chinese ischemic stroke subclassification. Front Neurol. 2011;2:6.","journal-title":"Front Neurol"},{"key":"1721_CR32","doi-asserted-by":"publisher","first-page":"19467","DOI":"10.1097\/MD.0000000000019467","volume":"99","author":"T Zhang","year":"2020","unstructured":"Zhang T, Jiang Y, Zhang S, Tie T, Ma Y. The association between homocysteine and ischemic stroke subtypes in Chinese: a meta-analysis. Medicine. 2020;99:19467.","journal-title":"Medicine"},{"key":"1721_CR33","first-page":"14","volume":"7","author":"MV Kravchenko","year":"2020","unstructured":"Kravchenko MV, Korostovtseva LS, Golovkova-Kucheriavaia MS, Bochkarev M, Sviryaev YV. Sleep breathing disorders in ischemic stroke: relationship with the localization and toast classification subtypes. Transl Med. 2020;7:14\u201320.","journal-title":"Transl Med"},{"key":"1721_CR34","doi-asserted-by":"crossref","unstructured":"Park S, Han MK, Kim B. Deep learning for prediction of mechanism in acute ischemic stroke using brain MRI. PREPRINT (Version 1) available at Research Square. 2021.","DOI":"10.21203\/rs.3.rs-604141\/v1"},{"key":"1721_CR35","doi-asserted-by":"publisher","first-page":"161","DOI":"10.5853\/jos.2014.16.3.161","volume":"16","author":"Y Ko","year":"2014","unstructured":"Ko Y, Lee S, Chung J-W, Han M-K, Park J-M, Kang K, Park T, Park S-S, Cho Y-J, Hong K-S, Lee K, Lee J, Kim D-E, Kim D-H, Cha J-K, Kim J-T, Choi JC, Shin D-I, Lee JS, Bae H-J. MRI-based algorithm for acute ischemic stroke subtype classification. J Stroke. 2014;16:161\u201372.","journal-title":"J Stroke"},{"key":"1721_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-020-01362-0","volume":"21","author":"J Fan","year":"2021","unstructured":"Fan J, Chen M, Luo J, et al. The prediction of asymptomatic carotid atherosclerosis with electronic health records: a comparative study of six machine learning models. BMC Med Inform Decis Mak. 2021;21:1\u20139.","journal-title":"BMC Med Inform Decis Mak"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-021-01721-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-021-01721-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-021-01721-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,5]],"date-time":"2022-01-05T12:06:16Z","timestamp":1641384376000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-021-01721-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,5]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["1721"],"URL":"https:\/\/doi.org\/10.1186\/s12911-021-01721-5","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,5]]},"assertion":[{"value":"11 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The ethics committee of the First Affiliated Hospital of Zhengzhou University approved the study and informed consents were obtained from participants. All methods were carried out in accordance with relevant guidelines and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"3"}}